In this work, we investigate a simple and must-known conditional generative framework based on Vector Quantised-Variational AutoEncoder (VQ-VAE) and Generative Pre-trained Transformer (GPT) for human motion generation from textural descriptions. We show that a simple CNN-based VQ-VAE with commonly used training recipes (EMA and Code Reset) allows us to obtain high-quality discrete representations. For GPT, we incorporate a simple corruption strategy during the training to alleviate training-testing discrepancy. Despite its simplicity, our T2M-GPT shows better performance than competitive approaches, including recent diffusion-based approaches. For example, on HumanML3D, which is currently the largest dataset, we achieve comparable performance on the consistency between text and generated motion (R-Precision), but with FID 0.116 largely outperforming MotionDiffuse of 0.630. Additionally, we conduct analyses on HumanML3D and observe that the dataset size is a limitation of our approach. Our work suggests that VQ-VAE still remains a competitive approach for human motion generation.

翻译：本研究探索了一种基于矢量量化变分自编码器（VQ-VAE）和生成式预训练Transformer（GPT）的简单且必要的条件生成框架，用于从文本描述生成人体运动。研究表明，采用常用训练策略（EMA和Code Reset）的简单CNN架构VQ-VAE可获得高质量离散表示。对于GPT，我们在训练过程中引入简单的损坏策略以缓解训练-测试差异。尽管方法简单，T2M-GPT在性能上优于包括近期扩散方法在内的竞争性方法。例如，在目前最大数据集HumanML3D上，我们在文本与生成运动的一致性（R精度）上取得可比性能，但FID指标0.116显著优于MotionDiffuse的0.630。此外，通过对HumanML3D的分析，我们观察到数据集规模限制了方法性能。本研究表明VQ-VAE仍是人体运动生成领域的有效方法。